© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15623
    Prev
    Next
    INDEX
    Explanations

    terms related to campaign finance and donations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "campaign" or "campaign finance"

    np_acts-logits-general · gemini-2.0-flash

    campaign finance contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ब्रेकडाउन
    -0.43
     culturel
    -0.39
     soud
    -0.36
     Infórmanos
    -0.34
    annelse
    -0.34
     Sado
    -0.34
    brada
    -0.34
     محفوظة
    -0.33
     résoudre
    -0.33
     culturally
    -0.33
    POSITIVE LOGITS
     campaign
    0.98
     fundraising
    0.94
     donors
    0.87
     Campaign
    0.86
    campaign
    0.85
     fundraiser
    0.85
    Campaign
    0.85
     Fundraising
    0.82
     donor
    0.78
    Fundraising
    0.77
    Activations Density 0.596%

    No Known Activations